Word Lists Lose: What 31 Attempts to Fool a Static Auditor for AI Agent Skills Taught Us
Word Lists Lose: What 31 Attempts to Fool a Static Auditor for AI Agent Skills Taught...
Tag archive
Word Lists Lose: What 31 Attempts to Fool a Static Auditor for AI Agent Skills Taught...

A skill is a file your agent obeys with your permissions. What went wrong in public registries, the trap that fooled our agent, and how to check one…
Skills Should Be Rented, Not Owned: Introducing Skill Airlock On 30 October 2026 I...

Claude Sonnet and Haiku reviewed 20 SKILL.md files we seeded with problems. Both caught hidden orders and keys; Haiku missed the rules you have to co…

The eight skills we released in September, run on Claude Sonnet and Haiku with the file and without it. Five clearly helped, two changed nothing, one…

What makes an agent pick up a SKILL.md, how to keep its rules checkable, and how to test it on a stronger and a weaker model, with a check that can f…
Open the root of an actively maintained repository in 2026 and there is a good chance you will find...
Wer 2026 die Wurzel eines aktiv gepflegten Repositorys öffnet, findet mit guter Wahrscheinlichkeit...
Open Agent Skills standard: SKILL.md replaces CLAUDE.md, AGENTS.md, and .cursorrules. Canonical directory, symlinks, validator — how to wire
Everyone's building AI chatbots. With Pin we did the opposite: buttons and templates are the main dish, the LLM is only a fallback. Here's the architecture behind that — why, for ordinary consumers, a deterministic button flow beats a clever free-form chat, and how one SKILL.md grows a LINE/TG button interface, an MCP server, and a webhook receiver all at once.

In today’s generative AI era, organizations struggle to query databases without models hallucinating...
A build-along for .NET developers: create one GitHub Copilot Skill (SKILL.md) that enforces Clean...